The field of time series forecasting is witnessing significant developments, with a focus on improving predictive accuracy and efficiency. Recent studies have explored the integration of hybrid approaches, such as combining fuzzy inference systems with traditional models, to enhance forecasting reliability. Additionally, innovations in transformer-based models and frequency filtering techniques are being applied to multivariate time series forecasting, demonstrating improved performance and computational efficiency. Noteworthy papers include the introduction of CASA, a CNN Autoencoder-based Score Attention mechanism, which reduces computational resources and improves model performance. The SCFormer model, a Structured Channel-wise Transformer with Cumulative Historical state, also shows promising results in multivariate time series forecasting. Other notable studies investigate the application of wavelet-based compression for efficient data management and the impact of lossy compression on Wi-Fi sensing accuracy.